The school cafeteria was a cacophony of shrieks and laughter, but all Susan could hear was the relentless pounding of her own heart. The flyer on the bulletin board. Mr. Thompson. The man who had made her doubt her intelligence, who had always found a way to make her feel inadequate. His presence in her son's life triggered a deep, visceral unease.

She retreated to the library, seeking refuge in the quiet stacks. But even there, the books seemed to whisper of forgotten anxieties, of past failures. She ran her hand along the spines, each title a reminder of the things she couldn't achieve. She had to run, to take her son and flee.

She imagined Mr. Thompson, standing over her son, judging his every move. She felt a burning sensation in her eyes. The thought of it made her want to scream. She had to escape this inescapable cycle.

Emotion: trapped

Cluster: Sadness / Despair
PC1 (Valence): -3.02 Negative
PC2 (Disposition): -0.80

Role in Research

This story is one of 1,000 stories generated for the emotion trapped. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 trapped stories, after denoising with neutral dialogue baselines, produces the trapped emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the trapped vector is projected through the unembedding matrix.

Promoted:
S0.573
ness0.401
无法0.366
hopeless0.360
😞0.353
Suppressed:
la-0.740
de-0.376
l-0.339
several-0.323
excitedly-0.322